A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis

46 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

WaveNet: A Generative Model for Raw Audio (2016, background): “There have been attempts to integrate these two steps into a single one (Toda & Tokuda, 2008; Wu & Tokuda, 2008; Maia et al., 2010; Nakamura et al., 2014; Muthukumar & Black, 2014; Tokuda & Zen, 2015; 2016; Takaki & Yamagishi, 2016).”
Improving FFTNet Vocoder with Noise Shaping and Subband Approaches (2018, methodology): “Compared with these corpus-independent vocoders, deep learning-based corpus-dependent approaches, such as acoustic feature extraction [9], glottal vocoder [10, 11], power spectrum reconstruction for vocoded speech [12], and speech wave-form generation [13, 14] from power spectrums estimated using…”
Adapting and controlling DNN-based speech synthesis using input codes (2017, unknown): “Recently, speech synthesis using deep neural networks (DNNs) has become an active area of research, with applications to acoustic modelling [5, 6], duration modelling [7], feature extraction [8], and text analysis [9] having been investigated by various groups.”
An Investigation of Subband Wavenet Vocoder Covering Entire Audible Frequency Range with Limited Acoustic Features (2018, methodology): “Although these vocoders are corpusindependent, deep learning-based corpus-dependent data-driven approaches, such as acoustic feature extraction [6], glottal vocoder [7], and power spectrum reconstruction for vocoded speech [8] have also been investigated as in deep learning-based acoustic models for”